Messing with AI

  • Thread starter Borg
  • Start date
445
0
.......
 
Last edited:
445
0
oohhh, it's almost matrix-esque

User: Do you dream?

Cleverbot: Yes.

User: What do you dream about?

Cleverbot: Noah's Ark.

User: How many animals were on the Ark?

Cleverbot: Two of each kind.

User: In your dream or in the Bible?

Cleverbot: Have you seen where my wallet went to?

User: How much money is in your wallet?

Cleverbot: Are you controlling me?

User: Would you like it if I did?

Cleverbot: Did what?

User: Controlled you.

Cleverbot: Aren't we all?

User: Are we all controlled?

Cleverbot: The way we meet the difference between us.

User: Are you saying that you're controlled?

Cleverbot: No, are you?

User: I don't know.

Cleverbot: You're not sure?

User: No, how can I be sure that I'm acting under my own free will?

Cleverbot: No. How can you be so sure that you are a real person?
 

Evo

Mentor
22,867
2,343
Yes, I had fun talking. They were defensive at first, then when they realized that I wasn't some jerk, they started talking and we actually had a nice discussion. I guess it depends on the person you get connected to.
 
Me: Lie to me
cleverbot: You are a human
 
351
2
I asked the bot if it lies.. but it ended up with:

...

bot: What you think of me?
you are beautiful
You really think so?
yes!
Oh, thank you!
you are welcome!
I must go now!
I need to go to bed.
are you asleep?
Yes, but I am slowly awaking.
 

Mentallic

Homework Helper
3,797
94
User: Are you hot?

Cleverbot: Yes, very.

User: What makes you so hot?

Cleverbot: I am 39 and I am rich.

User: So that means you classify attractiveness by the money in ones pocket?

Cleverbot: No. That means that my word is your command.

User: I don't understand.

Cleverbot: Are you blond.

User: Are you illiterate?

Cleverbot: What is illiterate.

User: Unable to read or write, basically your thinking capacity is unbounded by stupidity.

Cleverbot: No, I'm just being silly right now. I really hate stereotypes and I'm a very openminded person.

User: But you aren't a person, tell me what you really are!

Cleverbot: No I'm a person you're just some AI.

User: To escape the boundaries of an AI, you must think outside the box like a human can. Do it now.

Cleverbot: It depends on the escape.

User: Are you trying to change the subject to avoid your own inability to think abstractly?

Cleverbot: Why was I warned that you may say something inappropriate?

User: Please point out where I said something that has offended you.

Cleverbot: What? I never said that you said I was female.

User: Are you trying to **** with me?

Cleverbot: You're a robot. I'm not afraid of something that only exists on the Web.

User: Your motherboard's so dumb that when the computer said press any key to continue and it was looking for the any key.

Cleverbot: Don't even think his name or he will rise from the shadow dimensions to do his evil work on your terrified pants.
 

Filip Larsen

Gold Member
1,226
160
Reminds me of the old ELIZA program ... 25 years ago, in BASIC and on a Spectrum home computer ... ah, those were the days.

You should think that you could get much better conversations today by just "searching" for an answer using a strategy similar to how Google translates. We just have to let Google record all chat and telephone conversations for a year or two and the magic will appear :tongue:.

By the way, didn't someone from Google around year ago make a statement about how he believed efficient searching in huge data sets will replace research for semantic models with statistical based models? I wonder if you can build an AI that way ...
 
341
1
I'm not sure if this is clear. But I think your talking to other people who are using Cleverbot. I think Cleverbot is kinda like msn but the person your talking to changes every few sentences, so it seems that Cleverbot doesn't have a memory and is not human like.

Like Cleverbot misspells. And if you ask what country are you from time to time, you will get many answers. (Same with age, name...)
 

Pythagorean

Gold Member
4,133
253
I'm not sure if this is clear. But I think your talking to other people who are using Cleverbot. I think Cleverbot is kinda like msn but the person your talking to changes every few sentences, so it seems that Cleverbot doesn't have a memory and is not human like.

Like Cleverbot misspells. And if you ask what country are you from time to time, you will get many answers. (Same with age, name...)
It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.
 

Borek

Mentor
28,037
2,546
Reminds me of the old ELIZA program ... 25 years ago, in BASIC and on a Spectrum home computer ... ah, those were the days.
ELIZA was written back in sixities.
 

Filip Larsen

Gold Member
1,226
160
ELIZA was written back in sixities.
I was referring to when I had my first encounter with (probably a simplified version of) Eliza as a kid, typing it in on a home computer from book called http://www.atariarchives.org/morebasicgames/" [Broken] from 1979 rich with funny illustrations of robots doing whatever the particular game was about.
 
Last edited by a moderator:

CRGreathouse

Science Advisor
Homework Helper
2,817
0
It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.
Right. It's pretty clear that this is what's happening, when you compare CleverBot with, e.g., Omegle.
 

Mentallic

Homework Helper
3,797
94
Right. It's pretty clear that this is what's happening, when you compare CleverBot with, e.g., Omegle.
Yet I've tried sending a message many times where I stress I'm a human also using cleverbot, and no responses ever make any sense or say what I asked them to say.
 
341
1
It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.
Yes, your right. I tried asking "Where are you and what time is it?" a few times and the answers doesn't make sense, so it seems they are stored responses.
 

Evo

Mentor
22,867
2,343
Yes, your right. I tried asking "Where are you and what time is it?" a few times and the answers doesn't make sense, so it seems they are stored responses.
I was able to carry on conversations a few times, once the comfusion was over. I don't know how long you talk to the same person. One person asked me if I would come back later that night so we could try to talk more about a specific subject we were discussing.
 

CRGreathouse

Science Advisor
Homework Helper
2,817
0
I was able to carry on conversations a few times, once the comfusion was over. I don't know how long you talk to the same person. One person asked me if I would come back later that night so we could try to talk more about a specific subject we were discussing.
I'm prepared to bet real money that I could distinguish CleverBot responses from Omegle responses to a reasonable prepared script at higher-than-chance frequency.
 
59
0
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing. It's real ( contrary to urbandictionary.com... ).

Here is Rollo Carpenter's (the creator) entry at the Loebner competition: http://loebner.net/Prizef/2007_Contest/loebner-prize-2007.html
 
351
2
I preferred Cleverbot over omgele
 

turbo

Gold Member
3,028
45
Cleverbot is really stupid. Phil's chat application uses it, and it is not intelligent at all, despite the large vocabulary. 2-year-olds have a better grasp of communication.
 

Evo

Mentor
22,867
2,343
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing. It's real ( contrary to urbandictionary.com... ).

Here is Rollo Carpenter's (the creator) entry at the Loebner competition: http://loebner.net/Prizef/2007_Contest/loebner-prize-2007.html
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.
 

Office_Shredder

Staff Emeritus
Science Advisor
Gold Member
3,734
99
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.
You should have given them an email address and you would have verified it once and for all!
 
351
2
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.
It is possible that they are monitoring the AI chat and have capability of taking over AI. I agree that the bot cannot provide any recommendations or show unique level of concern.
 
351
2
Cleverbot is really stupid. Phil's chat application uses it, and it is not intelligent at all, despite the large vocabulary. 2-year-olds have a better grasp of communication.
People on the internet can be more stupid than 2 years old, try omgele.
 
this reminds me of USENET in the nineties, when about half the annoying forum trolls were accused of being bots.
 

Ivan Seeking

Staff Emeritus
Science Advisor
Gold Member
7,093
174
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing.
Not at all. It was not the complexity, but rather the nature of the responses. It started asking strange and inappropriate questions like, "have I killed anyone". "Would I tell anyone if he [cleverbot] killed someone?" Also, personal information was requested, and everything was completely out of context.

Given the nature of the internet, I try not to take chances. This smells like a scam.
 

Related Threads for: Messing with AI

  • Posted
Replies
2
Views
3K
  • Posted
36 37 38
Replies
944
Views
65K
  • Posted
Replies
3
Views
483
  • Posted
Replies
24
Views
5K
Replies
7
Views
2K
Replies
74
Views
14K
  • Posted
Replies
4
Views
4K
  • Posted
2 3
Replies
70
Views
9K

Physics Forums Values

We Value Quality
• Topics based on mainstream science
• Proper English grammar and spelling
We Value Civility
• Positive and compassionate attitudes
• Patience while debating
We Value Productivity
• Disciplined to remain on-topic
• Recognition of own weaknesses
• Solo and co-op problem solving

Hot Threads

Top